Chrominance Information Research Articles

Enhancing Image Dehazing Efficiency with Dual Colour Space Attentional Deep Networks

Aims and Background: Image dehazing is an essential task in computer-vision, aimed at enhancing the clarity and visibility of images degraded by fog and haze. Traditional methods often struggle with handling the complex scattering effects of haze and maintaining the natural colours of the scene. Objectives and Methodology: To address these challenges, we propose a novel approach termed Dual Colour Space Attentional Deep Network (DCSADN) for efficient image dehazing. Our method leverages the advantages of two-colour spaces: RGB and YCbCr, to boost the network's skill to capture both the luminance and chrominance information, thereby improving the dehazing performance. We employ a multi-stage training strategy to optimize the performance of the DCSADN. This multi-stage approach ensures that the network generalizes well across different types of haze conditions. Extensive experiments demonstrate the superiority of our method over state-of-the-art dehazing techniques. Results: The results indicate that our approach not only achieves higher quantitative scores in terms of Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) but also produces dehazed images with more natural colours and details. Conclusion: The findings reveal that the dual colour space processing and attentional modules are crucial for the enhanced performance of our method and providing a valuable tool for improving image quality in hazy conditions.

Robust Distribution‐Aware Color Correction for Single‐Shot Images

AbstractColor correction for photographed images is an ill‐posed problem. It is also a crucial initial step towards material acquisition for inverse rendering methods or pipelines. Several state‐of‐the‐art methods rely on reducing color differences for imaged reference color chart blocks of known color values to devise or optimize their solution. In this paper, we first establish through simulations the limitation of this minimality criteria which in principle results in overfitting. Next, we study and propose a few spatial distribution measures to augment the evaluation criteria. Thereafter, we propose a novel patch‐based, white‐point centric approach that processes luminance and chrominance information separately to improve on the color matching task. We compare our method qualitatively with several state‐of‐the art methods using our augmented evaluation criteria along with quantitative examinations. Finally, we perform rigorous experiments and demonstrate results to clearly establish the benefits of our proposed method.

Self-embedding reversible color-to-grayscale conversion with watermarking feature

This paper presents a self-embedding reversible color-to-grayscale conversion (RCGC) algorithm that makes good use of deep learning, vector quantization, and halftoning techniques to achieve its goals. By decoupling the luminance information of a pixel from its chrominance information, it explicitly controls the luminance error of both the conversion outputs and their corresponding reconstructed color images. It can also alleviate the burden of the deep learning network used to restore the embedded chrominance information during the reconstruction of the color image. Luminance-guided chrominance quantization and checkerboard-based halftoning are introduced in the paper to encode the chrominance information to be embedded while reference-guided inverse halftoning is proposed to restore the color image. Simulation results verify that its performance is remarkably superior to conventional state-of-art RCGC algorithms in various measures. In the aspect of authentication, embedding the watermark and chrominance information is realized with context-based pixel-wise encryption and a key-based watermark bit positioning mechanism, which makes us possible to locate tampered regions and prevent unauthorized use of the chrominance information.

DBENet: Dual-Branch Brightness Enhancement Fusion Network for Low-Light Image Enhancement

In this paper, we propose an end-to-end low-light image enhancement network based on the YCbCr color space to address the issues encountered by existing algorithms when dealing with brightness distortion and noise in the RGB color space. Traditional methods typically enhance the image first and then denoise, but this amplifies the noise hidden in the dark regions, leading to suboptimal enhancement results. To overcome these problems, we utilize the characteristics of the YCbCr color space to convert the low-light image from RGB to YCbCr and design a dual-branch enhancement network. The network consists of a CNN branch and a U-net branch, which are used to enhance the contrast of luminance and chrominance information, respectively. Additionally, a fusion module is introduced for feature extraction and information measurement. It automatically estimates the importance of corresponding feature maps and employs adaptive information preservation to enhance contrast and eliminate noise. Finally, through testing on multiple publicly available low-light image datasets and comparing with classical algorithms, the experimental results demonstrate that the proposed method generates enhanced images with richer details, more realistic colors, and less noise.

Fake Colorized Image Detection Based on Special Image Representation and Transfer Learning

Nowadays, images have become one of the most popular forms of communication as image editing tools have evolved. Image manipulation, particularly image colorization, has become easier, making it harder to differentiate between fake colorized images and actual images. Furthermore, the RGB space is no longer considered to be the best option for color-based detection techniques due to the high correlation between channels and its blending of luminance and chrominance information. This paper proposes a new approach for fake colorized image detection based on a novel image representation created by combining color information from three separate color spaces (HSV, Lab, and Ycbcr) and selecting the most different channels from each color space to reconstruct the image. Features from the proposed image representation are extracted based on transfer learning using the pre-trained CNNs ResNet50 model. The Support Vector Machine (SVM) approach has been used for classification purposes due to its high ability for generalization. Our experiments indicate that our proposed models outperform other state-of-the-art fake colorized image detection methods in several aspects.

Bas-relief modeling from RGB monocular images with regional division characteristics

Traditional Bas-relief modeling methods are often limited to inefficient and difficult to be altered after the product is formed. This paper presents a novel method for bas-relief modeling from RGB monocular images with regional division characteristics. The problem discussed in this paper involves edge detection, region division, height value recovery and three-dimensional reconstruction of image. In our framework, we can automatically obtain the pixel height of each area in the image and can adjust the concave–convex relationship of each image area to obtain a bas-relief modeling which can be printed directly in 3D. The edge detection algorithm used Gaussian difference pyramid to combine the luminance information and chrominance information of digital image; the regions of the RGB monocular image are divided by the improved connected-component labeling algorithm;and the 3D pixel point cloud of each region is calculated by the shape-from-shading algorithm. Different from previous work, our method can fully obtain the image height field data and completely restored the depth information,which makes it possible to use any RGB monocular image for bas-relief modeling. Experiments with groups of images show that our method can effectively generate bas-relief modeling.

CLASSIFICATION REVIEW OF RAW SUBJECTIVE SCORES TOWARDS STATISTICAL ANALYSIS

We proposed a no reference model for quality estimation based on compression artifacts which are principal factor for determining the QoE compared to varying depth range within compression. Moreover, in our past research work, contents with strong compression have been rejected by the Subjects who graded quality of distorted videos and judged unacceptable. The results of our proposed approach conrm that our subjective scores of 120 videos are related to control of visible spatial artifacts of reconstructed videos not distorted and with consideration of User Experience (UX), It was traced out by rening raw subjective scores, it happened due to coding of spatial and temporal perceptual information according to H.264 standards mentioned by ITU only for video quality assessment, i.e., instead of coding spatial of chrominance and temporal information of luminance plane, selected test sequences were coded within luminance plane for both spatial and temporal information

Embedding Guided End-to-End Framework for Robust Image Watermarking

In recent years, deep learning-based watermarking algorithms have received extensive attention. However, the existing algorithms mainly use the autoencoder to insert watermark automatically and ignore using the prior knowledge to guide the watermark embedding. In this paper, an end-to-end framework based on embedding guidance is proposed for robust image watermarking. It contains four modules, i.e., prior knowledge extractor, encoder, attacking simulator, and decoder. To guide the watermark embedding, the prior knowledge extractor providing chrominance and edge information of cover images is used to modify cover images before inserting the watermark by the encoder. To enhance the robustness of watermark extraction, the attacking simulator applying various differentiable attacks on the encoded images is introduced before extracting the watermark by the decoder. Experimental results show that the proposed algorithm achieves a good balance between invisibility and robustness and is superior to state-of-the-art algorithms.

Adjusted JPEG Quantization Tables in Support of GPS Maps

Image quality manipulating in JPEG is done by quantization tables. JPEG has two quantization tables – one table for the luminance information and one table for the chrominance information. These quantization tables have been designed in support of images with few sharp changes; however, typically most GPS image maps have many sharp changes and as a result, the images are not optimally compressed. The designers of the quantization tables have presumed that sharp changes in the colors will rarely occur. Therefore, they divide the values that represent sharp changes in the frequency space by large numbers and divide other values by smaller numbers. As a result, when there are sharp changes in an image, the proportional allocation for each kind of data in the compressed image is inappropriate and results in an inefficient compression. In this paper the standard quantization tables have been modified as to handle the different kinds of GPS image map data appropriately. Consequently, the experimental results show that images with sharp changes are compressed more efficiently when making use of the new quantization tables.

EMFusion: An unsupervised enhanced medical image fusion network

Existing image fusion methods always use the same representations for different modal medical images. Otherwise, they solve the fusion problem by subjectively defining characteristics to be preserved. However, it leads to the distortion of unique information and restricts the fusion performance. To address the limitations, this paper proposes an unsupervised enhanced medical image fusion network. We perform both surface-level and deep-level constraints for enhanced information preservation. The surface-level constraint is based on the saliency and abundance measurement to preserve the subjectively defined and intuitive characteristics. In the deep-level constraint, the unique information is objectively defined based on the unique channels of a pre-trained encoder. Moreover, in our method, the chrominance information of fusion results is also enhanced. It is because we use the high-quality details in structural images (e.g., MRI) to alleviate the mosaic in functional images (e.g., PET, SPECT). Both qualitative and quantitative experiments demonstrate the superiority of our method over the state-of-the-art fusion methods.

YuvConv: Multi-Scale Non-Uniform Convolution Structure Based on YUV Color Model

Since digital images are able to be encoded through the luminance-bandwidth-chrominance (YUV) mode, and the contribution of luminance information is greater than that of chrominance information for human visual perception, it can be inferred that the appropriate reduction of chrominance information in convolutional neural network does not disturb image object recognition. In this paper, we propose a new multi-scale non-uniform convolution called YuvConv, wherein the output feature map of the convolutional layer is regarded as an image. First, the output channels in the new convolution are divided into three kinds of components: Y, U, and V tensors. Then, the tensor Y is used to process luminance information, which is high-resolution and occupies more output channels. Next, the tensors U and V are low-resolution and use fewer channels to process chrominance information. Finally, the adjacent tensors (Y-U, Y-U-V, and U-V) are fused as the output of YuvConv. Experimental results indicate that the use of the YuvConv instead of the standard convolution can improve the performance of deep learning tasks, and it can also reduce memory consumption and computation cost.

A 3D Image Quality Assessment Method Based on Vector Information and SVD of Quaternion Matrix under Cloud Computing Environment

With the increasing demands of end-users to the visual perception in three-dimension (3D) image, quality assessment for 3D imageis dominantly required as the feedback information for multimedia transmission systems. In this paper, a novel full-reference quality assessment method by considering the depth and integral color information of 3D image under cloud computing environment is proposed. Based on the property of the depth information in 3D image, the depth map is firstly separated into different planes according to the perception of human visual system (HVS). Then, after express the image pixels of every separated plane through quaternions, the structural and energy information are separated by quaternion singular value decomposition (QSVD). The distortion of structural and energy in every plane are calculated in various formulas respectively. The final result is calculated in terms of the global score, which synthesizes the structural and energy distortion scores in every individual depth plane. It should be pointed out that the chrominance information is employed in our mechanism to evaluate the color image quality because of its useful characteristic for 3D color image quality assessment, and its spatial correlation is used for calculating structural distortion through vector cross-product. Our experimental results confirm that the proposed method has achieves better performance under cloud computing environments compared with other existing 3D image quality assessment methods.

Variational Single Image Dehazing for Enhanced Visualization

In this paper, we investigate the challenging task of removing haze from a single natural image. The analysis on the haze formation model shows that the atmospheric veil has much less relevance to chrominance than luminance, which motivates us to neglect the haze in the chrominance channel and concentrate on the luminance channel in the dehazing process. Besides, the experimental study illustrates that the YUV color space is most suitable for image dehazing. Accordingly, a variational model is proposed in the Y channel of the YUV color space by combining the reformulation of the haze model and the two effective priors. As we mainly focus on the Y channel, most of the chrominance information of the image is preserved after dehazing. The numerical procedure based on the alternating direction method of multipliers (ADMM) scheme is presented to obtain the optimal solution. Extensive experimental results on real-world hazy images and synthetic dataset demonstrate clearly that our method can unveil the details and recover vivid color information, which is competitive among many existing dehazing algorithms. Further experiments show that our model also can be applied for image enhancement.

Robust Localization of Interpolated Frames by Motion-Compensated Frame Interpolation Based on an Artifact Indicated Map and Tchebichef Moments

Motion-compensated frame interpolation (MCFI), a frame-interpolation technique to increase the motion continuity of low frame-rate video, can be utilized by counterfeiters for faking high bitrate video or splicing videos with different frame rates. For existing MCFI detectors, their performances are degraded under real-world scenarios such as H.264/AVC compression, noise, or blur. To address this issue, a robust MCFI detector is proposed to locate interpolated frames. By analyzing the distribution of residual energies within interpolated frames, we observe that there exist strong correlations between artifact regions and high residual energies. Thus, an artifact indicated map is introduced to select candidate artifact regions. Then, Tchebichef moments (TMs) are exploited to characterize the blurring effects or deformed structures among these regions. Specifically, the mean value of absolute high-order TMs of selected regions is used to model these temporal inconsistencies. Finally, a sliding window is adopted to locate interpolated frames, which are further refined by three post-processing operations. Chrominance information is also integrated with luminance information for robust identification of interpolated frames. Extensive experimental results show that compared with the state-of-the-art MCFI detectors, the proposed approach is more robust for compressed videos under various real-world scenarios.

Significance of processing chrominance information for scene classification: a review

The primary objective of this paper is to provide a detailed review of various works showing the role of processing chrominance information for color-to-grayscale conversion. The usefulness of perceptually improved color-to-grayscale converted images for scene classification is then studied as a part of this presented work. Various issues identified for the color-to-grayscale conversion and improved scene classification are presented in this paper. The review provided in this paper includes, review on existing feature extraction techniques for scene classification, various existing scene classification systems, different methods available in the literature for color-to-grayscale image conversion, benchmark datasets for scene classification and color-to-gray-scale image conversion, subjective evaluation and objective quality assessments for image decolorization. In the present work, a scene classification system is proposed using the pre-trained convolutional neural network and Support Vector Machines developed utilizing the grayscale images converted by the image decolorization methods. The experimental analysis on Oliva Torralba scene dataset shows that the color-to-grayscale image conversion technique has a positive impact on the performance of scene classification systems.

Kinship verification from face images in discriminative subspaces of color components

Automatic facial kinship verification is a challenging topic in computer vision due to its complexity and its important role in many applications such as finding missing children and forensics. This paper presents a Facial Kinship Verification (FKV) approach based on an automatic and more efficient two-step learning into color/texture information. Most of the proposed methods in automatic kinship verification from face images consider the luminance information only (i.e. gray-scale) and exclude the chrominance information (i.e. color) that can be helpful, as an additional cue, for predicting relationships. We explore the joint use of color-texture information from the chrominance and the luminance channels by extracting complementary low-level features from different color spaces. More specifically, the features are extracted from each color channel of the face image and fused to achieve better discrimination. We investigate different descriptors on the existing face kinship databases, illustrating the usefulness of color information, compared with the gray-scale counterparts, in seven various color spaces. Especially, we generate from each color space three subspaces projection matrices and then score fusion methodology to fuse three distances belonging to each test pair face images. Experiments on three benchmark databases, namely the Cornell KinFace, the KinFaceW (I & II) and the TSKinFace database, show superior results compared to the state of the art.

Fusion of Color Images Based on Fuzzy Transform and Spatial Frequency

Multiple images of a scene, captured using different imaging devices and containing complementary information, are required to be combined into a single fused image. The fused image, so obtained, should ideally contain all important features of individual input images. Further, color image processing is also gaining importance in most of the real-life applications. Color images provide better visual information and are highly suitable for human visual perception. Motivated by the gaining importance of color image processing, fusion of color images is proposed. The fusion algorithm is proposed in HSV color space where the luminance components of multiple input images, based on fuzzy transform and spatial frequency, are fused. The chrominance information of input images provides color to the fused image. The fused image contains all important information and possesses natural color appearance. Experiments performed on various pairs of visible–infrared and multifocus images demonstrate the superiority of the proposed algorithm over recent state-of-the-art image fusion algorithms.

A new method for image super-resolution with multi-channel constraints

Most recent learning-based image super-resolution (SR) methods have attracted much interest. This paper proposes a new SR method with multi-channel constraints, which integrates clustering, collaborative representation, and progressive multi-layer mapping relationships to reconstruct high-resolution (HR) color image. In order to collect chrominance information, the training patches from RGB channels are clustered into different subspaces, and a number of neighbor subsets are grouped. Then the optimization problem with color channel constraints is solved by using the classical gradient technique. Finally, a continuous reconstructive structure, which learns multi-layer mapping relationships between intermediate output and corresponding original HR image, is designed to obtain the desired HR image. Extensive experiments on several commonly used image SR testing datasets indicate that the proposed method achieves state-of-the-art image SR results.

Significance of perceptually relevant image decolorization for scene classification

A color image contains luminance and chrominance components representing the intensity and color information respectively. The objective of the work presented in this paper is to show the significance of incorporating the chrominance information for the task of scene classification. An improved color-to-grayscale image conversion algorithm by effectively incorporating the chrominance information is proposed using color-to-gay structure similarity index (C2G-SSIM) and singular value decomposition (SVD) to improve the perceptual quality of the converted grayscale images. The experimental result analysis based on the image quality assessment for image decolorization called C2G-SSIM and success rate (Cadik and COLOR250 datasets) shows that the proposed image decolorization technique performs better than 8 existing benchmark algorithms for image decolorization. In the second part of the paper, the effectiveness of incorporating the chrominance component in scene classification task is demonstrated using the deep belief network (DBN) based image classification system developed using dense scale invariant feature transform (SIFT) as features. The levels of chrominance information incorporated by the proposed image decolorization technique is confirmed by the improvement in the overall scene classification accuracy . Also, the overall scene classification performance is improved by the combination of models obtained using the proposed and the conventional decolorization methods.

High dynamic range imaging method based on image content adaptive matrix completion

High dynamic range (HDR) imaging usually produces ghosting artifacts, while the traditional matrix completion (MC) method may fail to completely remove the ghosts, without considering the motion characteristics of multi-exposure image. To solve this problem, this paper presents a new HDR imaging method based on content adaptive matrix completion of low dynamic range (LDR) image to remove the ghosts of HDR image. Firstly, according to the image luminance and chrominance information, the LDR image motion area is determined. Then, based on the priori information of motion, the regularization constraint intensity is adjusted in MC process to get each LDR image background information. Finally, a fusion strategy related to multiple exposures is proposed while the difference of details in each image area under different exposures is considered. Regular background sequences and cluttered background sequences are used for experiments. The experimental results demonstrate that, compared with the partial sum minimization of singular values-matrix completion method, the proposed method is more real-time and suitable for cluttered background sequences.